模式识别与人工智能
Saturday, Jul. 26, 2025 Home      About Journal      Editorial Board      Instructions      Ethics Statement      Contact Us                   中文
  2006, Vol. 19 Issue (5): 578-584    DOI:
Papers and Reports Current Issue| Next Issue| Archive| Adv Search |
Confusable Chinese Speech Recognition Based on HMM/SVM TwoLevel Architecture
WANG HuanLiang, HAN JiQing, LI HaiFeng, ZHENG TieRan
School of Computer, Harbin Institute of Technology, Harbin 150001

Download: PDF (633 KB)   HTML (1 KB) 
Export: BibTeX | EndNote (RIS)      
Abstract  The recognition rate for confusable speech is still low in stateoftheart Chinese speech recognition systems based on HMM. The inherent defects of HMM are analyzed, then a twolevelarchitecture recognition framework combining HMM and SVM is proposed. A confidence estimation module is adopted to improve the performance and efficiency of the system. The information obtained by Viterbi decoding is utilized to construct new classes of feature for SVM, which solves the problem that the conventional SVM cannot directly process variable length sequences. The relevant issues, such as confidence estimation, classification feature extraction and SVM recognizer construction, are addressed. The experimental results of confusable Chinese speech show that compared with the hybrid HMM/SVM based system the proposed method can highly improve the recognition rate with little impact on the running speed.
Key wordsSpeech Recognition      Confusable Speech      Hidden Markov Model (HMM)      Support Vector Machine (SVM)     
Received: 06 April 2005     
ZTFLH: TP391.4  
  TP181  
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
WANG HuanLiang
HAN JiQing
LI HaiFeng
ZHENG TieRan
Cite this article:   
WANG HuanLiang,HAN JiQing,LI HaiFeng等. Confusable Chinese Speech Recognition Based on HMM/SVM TwoLevel Architecture[J]. , 2006, 19(5): 578-584.
URL:  
http://manu46.magtech.com.cn/Jweb_prai/EN/      OR     http://manu46.magtech.com.cn/Jweb_prai/EN/Y2006/V19/I5/578
Copyright © 2010 Editorial Office of Pattern Recognition and Artificial Intelligence
Address: No.350 Shushanhu Road, Hefei, Anhui Province, P.R. China Tel: 0551-65591176 Fax:0551-65591176 Email: bjb@iim.ac.cn
Supported by Beijing Magtech  Email:support@magtech.com.cn